Identificazione di approcci matematici per la selezione di features radiomiche statisticamente significative per la caratterizzazione del tumore mammario e altri tumori solidi da immagini radiologiche cliniche di pazienti

Purpose: Focal pattern in multiple myeloma (MM) seems to be related to poorer survival and differentiation from diffuse to focal pattern on computed tomography (CT) has inter-reader variability. This study aims evaluate if Radiomic approach could help radiologists in differentiating diffuse from focal patterns on CT.
Methods: We retrospectively reviewed imaging data of 70 patients with MM with CT, PET-CT or MRI available before bone marrow transplant. Two general radiologist evaluated, in consensus, CT images to define a focal (at least one lytic lesion > 5 mm in diameter) or a diffuse (lesions < 5 mm, not osteoporosis) pattern. N = 104 Radiomics features were extracted and evaluated with an open source software. Results: We found, after feature reduction, 9 features were different (p < 0.05) in the diffuse and focal patterns AUC of the Radiologists versus Reference Standard was 0.64. Conclusion: A Radiomics approach improves radiological evaluation of focal and diffuse pattern of MM on CT.